Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to decorative ribbons and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achment
    -0.18
    lej
    -0.15
    leo
    -0.15
    usra
    -0.15
    linger
    -0.15
    planation
    -0.15
    ¾ç¤º
    -0.14
     Armour
    -0.14
    ringe
    -0.14
    urus
    -0.14
    POSITIVE LOGITS
    bons
    0.40
    osomal
    0.29
    bed
    0.25
    osome
    0.24
     rib
    0.23
    avir
    0.22
     cage
    0.22
     Rib
    0.21
    bing
    0.20
    ij
    0.19
    Act Density 0.004%

    No Known Activations